Towards Iris Presentation Attack Detection with Foundation Models

TL;DR

This paper investigates using foundation models DinoV2 and VisualOpenClip for iris presentation attack detection, demonstrating that fine-tuning these models with a small neural network can outperform existing deep learning methods, especially with limited data.

Contribution

It introduces a novel iris PAD approach leveraging foundation models and shows that fine-tuning these models can surpass state-of-the-art deep learning techniques.

Findings

Fine-tuned foundation models outperform existing deep learning methods.

Training from scratch yields better results with ample bona fide and attack images.

Foundation models demonstrate strong generalization in iris PAD tasks.

Abstract

Foundation models are becoming increasingly popular due to their strong generalization capabilities resulting from being trained on huge datasets. These generalization capabilities are attractive in areas such as NIR Iris Presentation Attack Detection (PAD), in which databases are limited in the number of subjects and diversity of attack instruments, and there is no correspondence between the bona fide and attack images because, most of the time, they do not belong to the same subjects. This work explores an iris PAD approach based on two foundation models, DinoV2 and VisualOpenClip. The results show that fine-tuning prediction with a small neural network as head overpasses the state-of-the-art performance based on deep learning approaches. However, systems trained from scratch have still reached better results if bona fide and attack images are available.